Assignment 8: Visualization - Making a bar race

How to do it?:

Open the Rmarkdown file of this assignment (link) in Rstudio.
Right under each question, insert a code chunk (you can use the hotkey Ctrl + Alt + I to add a code chunk) and code the solution for the question.
Knit the rmarkdown file (hotkey: Ctrl + Alt + K) to export an html.
Publish the html file to your Githiub Page.

Submission: Submit the link on Github of the assignment to Canvas

Install two packages gganimate and gifski then restart Rstudio. Using the Adult Census Income data, make an animation using geom_point and transition_states.

library(gganimate)

## Warning: package 'gganimate' was built under R version 4.3.3

## Warning: package 'ggplot2' was built under R version 4.3.3

library(ggplot2)
library(tidyverse)

## Warning: package 'tidyverse' was built under R version 4.3.3

## Warning: package 'tibble' was built under R version 4.3.3

## Warning: package 'tidyr' was built under R version 4.3.3

## Warning: package 'readr' was built under R version 4.3.3

## Warning: package 'purrr' was built under R version 4.3.3

## Warning: package 'dplyr' was built under R version 4.3.3

## Warning: package 'forcats' was built under R version 4.3.3

## Warning: package 'lubridate' was built under R version 4.3.3

library(knitr)

## Warning: package 'knitr' was built under R version 4.3.3

df = read_csv('adult_census.csv')

df <- df %>% 
  mutate(education.num = as.character(education.num),
         workclass = as.character(workclass))

df %>% ggplot(aes(x = fnlwgt,
           y = age, color=education.num))+
  geom_point()+
  transition_states(native.country)+
  labs(title = 'country: {closest_state}')

Using the Adult Census Income data, make an animation using geom_bar and transition_states.

df %>% ggplot(aes(x = age,
                  fill=sex))+
  geom_bar(position = 'fill')+
  transition_states(education.num) +
  labs(title = 'education.num: {closest_state}')

Use the WHO’s dataset at this link. Make a top-10 bar race by months between countries on the number of deaths by Covid 19 in 2021.

library(dplyr)
library(ggplot2)
library(gganimate)
library(lubridate)
library(readr)


df2 <- read_csv("https://covid19.who.int/WHO-COVID-19-global-data.csv")


df2$Date_reported <- as.Date(df2$Date_reported)


df2 <- df2 %>%
    filter(year(Date_reported) == 2021, !is.na(New_deaths), New_deaths > 0)


df2$month <- floor_date(df2$Date_reported, "month")


monthly_deaths <- df2 %>%
    group_by(month, Country) %>%
    summarise(total_deaths = sum(New_deaths, na.rm = TRUE), .groups = 'drop')


ranked_deaths <- monthly_deaths %>%
    group_by(month) %>%
    mutate(rank = rank(-total_deaths)) %>%
    filter(rank <= 10)


a1 <- ggplot(ranked_deaths, aes(x = rank, y = total_deaths, fill = Country, label = Country)) +
    geom_col() +
    geom_text(aes(y = total_deaths, label = Country), hjust = 1.4) +
    coord_flip(clip = "off", expand = FALSE) +
    scale_x_reverse() +
    labs(title = 'Top 10 Countries by COVID-19 Deaths: Month {closest_state}', x = '', y = 'Total Deaths', fill = 'Country') +
    theme(plot.title = element_text(hjust = 0.5, size = 22),
          axis.ticks.y = element_blank(),
          axis.text.y = element_blank()) +
    transition_states(month, transition_length = 2, state_length = 1) +
    ease_aes("cubic-in-out")

animate(a1, nframes = 400)

Make a bar race using a dataset of your own interest. You may use the dataset that we use in class (https://covidtracking.com/data/download/all-states-history.csv) but you should make a different bar racev from ones in the slides.

# Load necessary libraries
library(dplyr)
library(ggplot2)
library(gganimate)
library(lubridate)
library(readr)
df2 <- read_csv("https://covid19.who.int/WHO-COVID-19-global-data.csv")

df2$Date_reported <- as.Date(df2$Date_reported)

df2_2022 <- df2 %>%
  filter(year(Date_reported) == 2022, !is.na(New_cases), New_cases > 0)


df2_2022$month <- floor_date(df2_2022$Date_reported, "month")


d1 <- df2_2022 %>%
  group_by(month, Country) %>%
  summarise(total_new_cases = sum(New_cases, na.rm = TRUE), .groups = 'drop')


d2 <- d1 %>%
  group_by(month) %>%
  mutate(rank = rank(-total_new_cases))


d3 <- d2 %>%
  filter(rank <= 5)


a1 <- d3 %>%
  ggplot(aes(x = rank, y = total_new_cases, group = Country, fill = Country, label = Country)) +
  geom_col() +
  geom_text(aes(y = total_new_cases, label = Country), hjust = 1.4) +
  coord_flip(clip = "off", expand = FALSE) +
  scale_x_reverse() +
  labs(title = 'Top 5 Countries by New COVID-19 Cases: Month {closest_state}', 
       x = '', 
       y = 'Total New Cases', 
       fill = 'Country') +
  theme(plot.title = element_text(hjust = 0.5, size = 22),
        axis.ticks.y = element_blank(),
        axis.text.y = element_blank()) +
  transition_states(month, transition_length = 2, state_length = 1) +
  ease_aes("cubic-in-out")


animate(a1, nframes = 400)